On view-invariant gait recognition: a feature selection solution

Jia, Ning; Sanchez, Victor; Li, Chang-Tsun

Abstract

The authors present an improved feature selection solution for the view-invariant gait recognition problem, based on their previously proposed method called view-invariant feature selector (ViFS), which automatically reconstruct an optimised gallery template from a set of multi-view gallery templates. They improved ViFS by introducing a constraint to make sure that the reconstructed features have the same scale as the original features, thus reducing the number of misclassifications caused by data misalignment. They evaluate the improved ViFS on the CASIA B and OU-ISIR large population datasets by performing a wide range of comparative studies in order to explore and confirm its effectiveness. Evaluation results indicate that the proposed framework is very effective for view-invariant gait recognition tasks.

Citation

Jia, N., Sanchez, V., & Li, C.-T. (2018). On view-invariant gait recognition: a feature selection solution. IET Biometrics, 7(4), 287-295. https://doi.org/10.1049/iet-bmt.2017.0151

• Journal Article Type: Article
• Acceptance Date: Feb 26, 2018
• Online Publication Date: May 8, 2018
• Publication Date: Jul 1, 2018
• Deposit Date: Jul 5, 2018
• Publicly Available Date: Jul 5, 2018
• Journal: IET Biometrics
• Print ISSN: 2047-4938
• Electronic ISSN: 2047-4946
• Publisher: Institution of Engineering and Technology (IET)
• Peer Reviewed: Peer Reviewed
• Volume: 7
• Issue: 4
• Pages: 287-295
• DOI: https://doi.org/10.1049/iet-bmt.2017.0151
• Public URL: https://durham-repository.worktribe.com/output/1327066